Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to cautionary measures and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isers
    -0.19
    izers
    -0.18
    isation
    -0.18
    thesis
    -0.17
    IZATION
    -0.17
    ters
    -0.17
    IFICATION
    -0.16
    atisation
    -0.16
    gers
    -0.16
    TERS
    -0.16
    POSITIVE LOGITS
    img
    0.30
    ng
    0.27
    eing
    0.27
    uating
    0.26
    inf
    0.26
    ring
    0.26
    ulating
    0.25
    Ing
    0.25
    uing
    0.25
    ining
    0.25
    Act Density 0.065%

    No Known Activations